---
base_model: distilbert-base-uncased
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: distilbert-fake-reviews-finetuned
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# distilbert-fake-reviews-finetuned

This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the [Fake Reviews Dataset](https://www.kaggle.com/datasets/thearijitdas/fake-reviews-dataset) (processed and cleaned version of [🚨 Fake Reviews Dataset](https://www.kaggle.com/datasets/mexwell/fake-reviews-dataset)), containing 20k fake reviews and 20k real product reviews. OR = Original reviews (presumably human created and authentic); CG = Computer-generated fake reviews.  
It achieves the following results on the evaluation set:
- Loss: 0.1241

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.172         | 1.0   | 2022 | 0.0987          |
| 0.003         | 2.0   | 4044 | 0.1477          |
| 0.0002        | 3.0   | 6066 | 0.1241          |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1